CN117074627A - Medical laboratory air quality monitoring system based on artificial intelligence - Google Patents
Medical laboratory air quality monitoring system based on artificial intelligence Download PDFInfo
- Publication number
- CN117074627A CN117074627A CN202311335738.9A CN202311335738A CN117074627A CN 117074627 A CN117074627 A CN 117074627A CN 202311335738 A CN202311335738 A CN 202311335738A CN 117074627 A CN117074627 A CN 117074627A
- Authority
- CN
- China
- Prior art keywords
- air quality
- quality monitoring
- time
- node
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 173
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000010586 diagram Methods 0.000 claims abstract description 38
- 230000005856 abnormality Effects 0.000 claims abstract description 30
- 238000000547 structure data Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000010276 construction Methods 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 12
- 239000000809 air pollutant Substances 0.000 claims description 9
- 231100001243 air pollutant Toxicity 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000003915 air pollution Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000009471 action Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a computer specifically programmed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Combustion & Propulsion (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a medical laboratory air quality monitoring system based on artificial intelligence, which comprises: the system comprises a data acquisition module, a data preprocessing module, a space-time diagram structure data construction module, an air quality monitoring model construction module and an air quality abnormality monitoring module. The invention belongs to the technical field of air quality monitoring, in particular to a medical laboratory air quality monitoring system based on artificial intelligence, which combines a space weighted adjacent matrix with a time weighted adjacent matrix optimized based on a weighted average method so as to complete the construction of space-time diagram structural data; an air quality monitoring model is built in a coding-decoding mode, time context information is embedded, and connection weights are embedded and restored through calculation nodes, so that reconstruction and anomaly detection of air quality monitoring data are realized.
Description
Technical Field
The invention belongs to the technical field of air quality monitoring, and particularly relates to an artificial intelligence-based medical laboratory air quality monitoring system.
Background
The air quality can be monitored in real time through the air quality monitoring system, the safety of a laboratory is improved, and the quality and the reliability of medical experiments are ensured. However, the traditional air quality monitoring is based on the time correlation of a single air quality monitoring station to perform abnormality detection, so that the problem that the space correlation between the air quality monitoring stations is ignored and the accuracy of the air quality monitoring is reduced exists; the traditional air quality monitoring model has the problems that abnormality cannot be accurately detected when a large amount of data is faced, false alarm or missing alarm is caused, and the time and space context information cannot be fully utilized to optimize detection.
Disclosure of Invention
Aiming at the situation, in order to overcome the defects of the prior art, the invention provides an artificial intelligence-based medical laboratory air quality monitoring system, and aims at solving the problems that the traditional air quality monitoring is based on the time correlation of a single air quality monitoring station for abnormality detection, the space correlation among the air quality monitoring stations is ignored and the accuracy of the air quality monitoring is reduced; aiming at the problems that the traditional air quality monitoring model cannot accurately detect abnormality when facing a large amount of data, false alarm or missing alarm is caused, and the detection cannot be optimized by fully utilizing the time and space context information, the scheme adopts an encoding-decoding mode to construct the air quality monitoring model, embeds the time context information, embeds each day and each hour in one day as the time context information, extracts time related characteristics better, embeds and recovers connection weights through computing nodes, realizes the reconstruction and abnormality detection of the air quality monitoring data, can accurately capture abnormal states, and improves the accuracy and efficiency of air quality abnormality monitoring.
The invention provides an artificial intelligence-based medical laboratory air quality monitoring system which comprises a data acquisition module, a data preprocessing module, a space-time diagram structure data building module, an air quality monitoring model building module and an air quality abnormality monitoring module, wherein the air quality monitoring module is used for acquiring a space-time diagram structure data of a medical laboratory;
the data acquisition module acquires air quality monitoring data in a medical laboratory;
the data preprocessing module deletes incorrect, irrelevant and repeated air quality monitoring data existing in the historical air quality monitoring data set and carries out missing value processing and data normalization processing;
the space-time diagram structure data constructing module combines the space weighted adjacent matrix and the time weighted adjacent matrix optimized based on the weighted average method, so that the space-time diagram structure data is constructed;
the air quality monitoring model building module builds an air quality monitoring model in a coding-decoding mode, embeds time context information, and realizes reconstruction and anomaly detection of air quality monitoring data by embedding and recovering connection weights through computing nodes;
the air quality abnormality monitoring module judges whether the air quality in the medical laboratory is in an abnormal state or not based on a preset abnormality threshold value, and completes air quality abnormality monitoring.
Further, the data acquisition module deploys a plurality of air quality monitoring stations in the medical laboratory, acquires air quality monitoring data in the medical laboratory through the air quality monitoring stations, constructs a historical air quality monitoring data set by collecting historical air quality monitoring data in the medical laboratory, and constructs a real-time air quality monitoring data set by acquiring real-time air quality monitoring data in the medical laboratory.
Further, the data preprocessing module deletes incorrect, irrelevant and repeated air quality monitoring data existing in the historical air quality monitoring data set, and performs missing value processing and data normalization processing on the historical air quality monitoring data set.
Further, the space-time diagram construction structure data module is connected with all air quality monitoring stations in a medical laboratory, takes each air quality monitoring station as a node, and constructs space-time diagram construction data based on a historical air quality monitoring data set, and specifically comprises the following contents:
the construction of the space correlation data is used for representing the space correlation of the air quality monitoring data by constructing the space correlation data, and the content is as follows:
the connection weight between the nodes is calculated by the following formula:
；
where z is the connection weight, i and j are node indexes, exp () is an exponential function, dist (i, j) is the distance between node i and node j, and α is a parameter controlling the width of neighboring nodes;
a spatial weighted adjacency matrix is established using the following formula:
；
wherein G is Z Is a spatial weighted adjacency matrix, N1 is the number of nodes;
the construction of the time-related data, which is used for representing the time correlation of the air quality monitoring data, comprises the following steps:
calculating a correlation coefficient, respectively calculating a pearson moment correlation coefficient, a spearman order correlation coefficient and a kendel order correlation coefficient of air pollutant monitoring values between any two nodes based on a historical air quality monitoring data set, and optimizing by using a weighted average method to obtain a final correlation coefficient, wherein the formula is as follows:
；
；
；
；
；
wherein B is i And B j The air pollution monitor values of node i and node j respectively,and->Air pollutant monitoring values of node I and node j on feature e, respectively, I being the feature quantity of the air quality monitoring data, +.>And->Air pollutant monitoring values of node i and node j on feature f, respectively, e and f being feature indices of air quality monitoring data, +.>And->Respectively B i And B j Arithmetic mean value of d e Is the air pollution monitoring difference between node i and node j on feature e, sgn () is a sign function, ω p 、ω s And omega k Weights of the pearson moment correlation coefficient, the spearman order correlation coefficient and the kendel order correlation coefficient, respectively, +.>、/>And->Respectively B i And B j Is a pearson product moment correlation coefficient, a spearman order correlation coefficient and a kendel order correlation coefficient,/>Is B i And B j Final correlation coefficient of (a);
a time weighted adjacency matrix is established, and the following formula is used:
；
wherein H is Z Is a time weighted adjacency matrix;
and constructing space-time diagram structure data, and obtaining a space-time weighted adjacent matrix based on the space weighted adjacent matrix and the time weighted adjacent matrix to obtain the space-time diagram structure data, wherein the formula is as follows:
Z（t）=G z H z ；
Q={q 1 ，q 2 ，…，q N1 }；
A（t）=（Q，γ，Z（t））；
where Q is a node set, Q is a node, a (t) is space-time diagram structure data at time t, γ is a connection set between nodes, and Z (t) is a space-time weighted adjacency matrix at time t.
Further, the air quality monitoring model constructing module constructs an air quality monitoring model based on space-time structural diagram data A (t) of a historical air quality monitoring data set, and specifically comprises the following contents:
encoding, performing encoding to obtain low-dimensional graph embedding, wherein the content is as follows:
the node embedding is calculated based on the GraphSAGE algorithm, and the formula is as follows:
；
；
in the method, in the process of the invention,is the embedding of node i at time t, q j Is node j, N i (t) is a node set adjacent to node i at time t, N j (t) is the set of nodes adjacent to node j at time t, z ij (t) is the connection weight of node i and node j at time t, +.>Is the embedding of node j at the first layer of time t, d l Is the embedded size of layer l;
updating node embedding of the next layer, wherein the formula is as follows:
；
；
wherein Z is l Is the connection weight matrix of layer l, concat is the aggregation operator, reLU is a nonlinear function,is the embedded estimate of the first +1 layer of node i at time t, +.>Is the embedding of node i at the first +1 layer of time t,is->The L2 norm of (2);
embedding time context information, wherein air quality monitoring data are periodic within u weeks v days, and embedding information h corresponding to the corresponding day in u weeks week Information h corresponding to the corresponding hour embedded in v days hour ；
Computational graph embedding, the formula used is as follows:
；
；
in the formula, h A (t) is the time t at which the ReLU function will be usedGraph embedding to low dimension>Is the final graph embedding combined at time t, Z A Is a weight matrix of the space-time structural diagram data A (t), is +.>The node i is embedded from the 1 st layer to the L th layer at the time t, and L is the embedded layer number;
decoding, the content is as follows:
the recovery node is embedded using the following formula:
；
in the method, in the process of the invention,is the restored node embedded->Is a weight matrix to be trained;
the single node embedding is resumed using the following formula:
；
in the formula, h i (t) is the embedding of node i at time t, and un stack is the cancel stack function;
the connection weights are restored using the following formula:
；
；
；
；
wherein d o Is the dimension of the connection weight, d L Is the number of layers in which the node is embedded,and->Is a weight matrix, h j (t) is the embedding of node j at time t,/->Is the estimated value of the connection weight of node i and node j at time t, z ij (t) is the connection weight of node i and node j at time t, σ is the Sigmoid function;
the reconstruction error is calculated using the MSE loss function, using the following formula:
；
where K (t) is the reconstruction error at time t, gamma is the connection set at time t, e ij Is an index of the connection relationship.
Further, the air quality abnormality monitoring module presets an abnormality threshold delta, a real-time air quality monitoring data set is input into the air quality monitoring model, when the reconstruction error K (t) is not less than delta, the air quality in the medical laboratory is in an abnormal state, and the system sends an alarm signal.
By adopting the scheme, the beneficial effects obtained by the invention are as follows:
(1) Aiming at the problem that the traditional air quality monitoring is based on the time correlation of a single air quality monitoring station to detect the abnormality, the spatial correlation among the air quality monitoring stations is ignored and the accuracy of the air quality monitoring is reduced, the space weighting adjacent matrix and the time weighting adjacent matrix are combined, so that the construction of space-time diagram structural data is completed, each air quality monitoring station is used as a node, the connection weight among the nodes is calculated, and a plurality of indexes are comprehensively considered on the time weighting adjacent matrix, so that the air quality monitoring model can better capture the change rule of the air quality monitoring data in time and space, and the accuracy and the interpretability of the air quality monitoring model are improved.
(2) Aiming at the problems that the traditional air quality monitoring model cannot accurately detect abnormality when facing a large amount of data, false alarm or missing alarm is caused, and the detection cannot be optimized by fully utilizing the time and space context information, the scheme adopts an encoding-decoding mode to construct the air quality monitoring model, embeds the time context information, embeds each day and each hour in one day as the time context information, extracts time related characteristics better, embeds and recovers connection weights through computing nodes, realizes the reconstruction and abnormality detection of the air quality monitoring data, can accurately capture abnormal states, and improves the accuracy and efficiency of air quality abnormality monitoring.
Drawings
FIG. 1 is a schematic diagram of an artificial intelligence based medical laboratory air quality monitoring system provided by the present invention;
FIG. 2 is a schematic diagram of a data preprocessing module;
FIG. 3 is a schematic diagram of a building space-time diagram structure data module;
FIG. 4 is a schematic diagram of a module for constructing an air quality monitoring model.
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention; all other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "top," "bottom," "inner," "outer," and the like indicate orientation or positional relationships based on those shown in the drawings, merely to facilitate description of the invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention.
Referring to fig. 1, the medical laboratory air quality monitoring system based on artificial intelligence provided by the invention comprises a data acquisition module, a data preprocessing module, a space-time diagram structure data building module, an air quality monitoring model building module and an air quality abnormality monitoring module;
the data acquisition module acquires air quality monitoring data in a medical laboratory;
the data preprocessing module deletes incorrect, irrelevant and repeated air quality monitoring data existing in the historical air quality monitoring data set and carries out missing value processing and data normalization processing;
the space-time diagram structure data constructing module combines the space weighted adjacent matrix and the time weighted adjacent matrix optimized based on the weighted average method, so that the space-time diagram structure data is constructed;
the air quality monitoring model building module builds an air quality monitoring model in a coding-decoding mode, embeds time context information, and realizes reconstruction and anomaly detection of air quality monitoring data by embedding and recovering connection weights through computing nodes;
the air quality abnormality monitoring module judges whether the air quality in the medical laboratory is in an abnormal state or not based on a preset abnormality threshold value, and completes air quality abnormality monitoring.
In a second embodiment, referring to fig. 1, the data acquisition module deploys a plurality of air quality monitoring stations in a medical laboratory based on the above embodiment, acquires air quality monitoring data in the medical laboratory through the air quality monitoring stations, constructs a historical air quality monitoring dataset by collecting historical air quality monitoring data in the medical laboratory, and constructs a real-time air quality monitoring dataset by collecting real-time air quality monitoring data in the medical laboratory.
Embodiment III referring to FIGS. 1 and 2, the data preprocessing module deletes incorrect, uncorrelated and repeated air quality monitoring data existing in the historical air quality monitoring data set, and performs missing value processing and data normalization processing on the historical air quality monitoring data set based on the embodiment.
Referring to fig. 1 and 3, in this embodiment, based on the above embodiment, a space-time diagram structure data module is constructed to connect all air quality monitoring stations in a medical laboratory, and uses each air quality monitoring station as a node, and constructs space-time diagram structure data based on a historical air quality monitoring data set, which specifically includes the following contents:
the construction of the space correlation data is used for representing the space correlation of the air quality monitoring data by constructing the space correlation data, and the content is as follows:
the connection weight between the nodes is calculated by the following formula:
；
where z is the connection weight, i and j are node indexes, exp () is an exponential function, dist (i, j) is the distance between node i and node j, and α is a parameter controlling the width of neighboring nodes;
a spatial weighted adjacency matrix is established using the following formula:
；
wherein G is Z Is a spatial weighted adjacency matrix, N1 is the number of nodes;
the construction of the time-related data, which is used for representing the time correlation of the air quality monitoring data, comprises the following steps:
calculating a correlation coefficient, respectively calculating a pearson moment correlation coefficient, a spearman order correlation coefficient and a kendel order correlation coefficient of air pollutant monitoring values between any two nodes based on a historical air quality monitoring data set, and optimizing by using a weighted average method to obtain a final correlation coefficient, wherein the formula is as follows:
；
；
；
；
；
wherein B is i And B j The air pollution monitor values of node i and node j respectively,and->Air pollutant monitoring values of node I and node j on feature e, respectively, I being the feature quantity of the air quality monitoring data, +.>And->Air pollutant monitoring values of node i and node j on feature f, respectively, e and f being feature indices of air quality monitoring data, +.>And->Respectively B i And B j Arithmetic mean value of d e Is the air pollution monitoring difference between node i and node j on feature e, sgn () is a sign function, ω p 、ω s And omega k Weights of the pearson moment correlation coefficient, the spearman order correlation coefficient and the kendel order correlation coefficient, respectively, +.>、/>And->Respectively B i And B j Is a pearson product moment correlation coefficient, a spearman order correlation coefficient and a kendel order correlation coefficient,/>Is B i And B j Final correlation coefficient of (a);
a time weighted adjacency matrix is established, and the following formula is used:
；
wherein H is Z Is a time weighted adjacency matrix;
and constructing space-time diagram structure data, and obtaining a space-time weighted adjacent matrix based on the space weighted adjacent matrix and the time weighted adjacent matrix to obtain the space-time diagram structure data, wherein the formula is as follows:
Z（t）=G z H z ；
Q={q 1 ，q 2 ，…，q N1 }；
A（t）=（Q，γ，Z（t））；
where Q is a node set, Q is a node, a (t) is space-time diagram structure data at time t, γ is a connection set between nodes, and Z (t) is a space-time weighted adjacency matrix at time t.
By executing the operation, the problem that the space correlation among the air quality monitoring stations is ignored and the accuracy of the air quality monitoring is reduced exists in the traditional air quality monitoring based on the time correlation of a single air quality monitoring station is solved.
An embodiment five, referring to fig. 1 and 4, in which the air quality monitoring model building module builds an air quality monitoring model based on the spatiotemporal structural data a (t) of the historical air quality monitoring dataset based on the above embodiment, specifically includes the following:
encoding, performing encoding to obtain low-dimensional graph embedding, wherein the content is as follows:
the node embedding is calculated based on the GraphSAGE algorithm, and the formula is as follows:
；
；
in the method, in the process of the invention,is the embedding of node i at time t, q j Is node j, N i (t) is a node set adjacent to node i at time t, N j (t) is the set of nodes adjacent to node j at time t, z ij (t) is the connection weight of node i and node j at time t, +.>Is the embedding of node j at the first layer of time t, d l Is the embedded size of layer l;
updating node embedding of the next layer, wherein the formula is as follows:
；
；
wherein Z is l Is the connection weight matrix of layer l, concat is the aggregation operator, reLU is a nonlinear function,is the embedded estimate of the first +1 layer of node i at time t, +.>Is the embedding of node i at the first +1 layer of time t,is->The L2 norm of (2);
embedding time context information, wherein air quality monitoring data are periodic within u weeks v days, and embedding information h corresponding to the corresponding day in u weeks week Information h corresponding to the corresponding hour embedded in v days hour ；
Computational graph embedding, the formula used is as follows:
；
；
in the formula, h A (t) is the time t at which the ReLU function will be usedGraph embedding to low dimension>Is the final graph embedding combined at time t, Z A Is a weight matrix of the space-time structural diagram data A (t), is +.>The node i is embedded from the 1 st layer to the L th layer at the time t, and L is the embedded layer number;
decoding, the content is as follows:
the recovery node is embedded using the following formula:
；
in the method, in the process of the invention,is the restored node embedded->Is a weight matrix to be trained;
the single node embedding is resumed using the following formula:
；
in the formula, h i (t) is the embedding of node i at time t, and un stack is the cancel stack function;
the connection weights are restored using the following formula:
；
；
；
；
wherein d o Is the dimension of the connection weight, d L Is the number of layers in which the node is embedded,and->Is a weight matrix, h j (t) is the embedding of node j at time t,/->Is the estimated value of the connection weight of node i and node j at time t, z ij (t) is the connection weight of node i and node j at time t, σ is the Sigmoid function;
the reconstruction error is calculated using the MSE loss function, using the following formula:
；
where K (t) is the reconstruction error at time t and γ is the timeConnection set of t, e ij Is an index of the connection relationship.
By executing the above operation, aiming at the problems that the traditional air quality monitoring model cannot accurately detect abnormality when facing a large amount of data, misinformation or missing report is caused, and the detection cannot be optimized by fully utilizing the time and space context information, the scheme adopts an encoding-decoding mode to construct the air quality monitoring model, embeds the time context information, embeds each day in a week and each hour in a day as the time context information, extracts time-related characteristics better, embeds and recovers connection weights through computing nodes, realizes the reconstruction and abnormality detection of the air quality monitoring data, can accurately capture abnormal states, and improves the accuracy and efficiency of air quality abnormality monitoring.
In a sixth embodiment, referring to fig. 1, the air quality anomaly monitoring module sets an anomaly threshold δ in advance, inputs a real-time air quality monitoring data set into the air quality monitoring model, and when the reconstruction error K (t) is greater than or equal to δ, the air quality in the medical laboratory is in an anomaly state, and the system sends an alarm signal.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
The invention and its embodiments have been described above with no limitation, and the actual construction is not limited to the embodiments of the invention as shown in the drawings. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (6)
1. Medical laboratory air quality monitoring system based on artificial intelligence, its characterized in that: the system comprises a data acquisition module, a data preprocessing module, a space-time diagram structure data construction module, an air quality monitoring model construction module and an air quality abnormality monitoring module;
the data acquisition module acquires air quality monitoring data in a medical laboratory;
the data preprocessing module deletes incorrect, irrelevant and repeated air quality monitoring data existing in the historical air quality monitoring data set and carries out missing value processing and data normalization processing;
the space-time diagram structure data constructing module combines the space weighted adjacent matrix and the time weighted adjacent matrix optimized based on the weighted average method, so that the space-time diagram structure data is constructed;
the air quality monitoring model building module builds an air quality monitoring model in a coding-decoding mode, embeds time context information, and realizes reconstruction and anomaly detection of air quality monitoring data by embedding and recovering connection weights through computing nodes;
the air quality abnormality monitoring module judges whether the air quality in the medical laboratory is in an abnormal state or not based on a preset abnormality threshold value, and completes air quality abnormality monitoring.
2. The artificial intelligence based medical laboratory air quality monitoring system of claim 1, wherein: the building space-time diagram structure data module is connected with all air quality monitoring stations in a medical laboratory, takes each air quality monitoring station as a node, and builds space-time diagram structure data based on a historical air quality monitoring data set, and specifically comprises the following contents:
the construction of the space correlation data is used for representing the space correlation of the air quality monitoring data by constructing the space correlation data, and the content is as follows:
the connection weight between the nodes is calculated by the following formula:
；
where z is the connection weight, i and j are node indexes, exp () is an exponential function, dist (i, j) is the distance between node i and node j, and α is a parameter controlling the width of neighboring nodes;
a spatial weighted adjacency matrix is established using the following formula:
；
wherein G is Z Is a spatial weighted adjacency matrix, N1 is the number of nodes;
the construction of the time-related data, which is used for representing the time correlation of the air quality monitoring data, comprises the following steps:
calculating a correlation coefficient, respectively calculating a pearson moment correlation coefficient, a spearman order correlation coefficient and a kendel order correlation coefficient of air pollutant monitoring values between any two nodes based on a historical air quality monitoring data set, and optimizing by using a weighted average method to obtain a final correlation coefficient, wherein the formula is as follows:
；
；
；
；
；
wherein B is i And B j The air pollution monitor values of node i and node j respectively,and->Air pollutant monitoring values of node I and node j on feature e, respectively, I being the feature quantity of the air quality monitoring data, +.>And->Air pollutant monitoring values of node i and node j on feature f, respectively, e and f being feature indices of air quality monitoring data, +.>And->Respectively B i And B j Arithmetic mean value of d e Is the air pollution monitoring difference between node i and node j on feature e, sgn () is a sign function, ω p 、ω s And omega k Respectively, pearson moment correlation coefficient and sWeights of the Pelman order correlation coefficient and Kendall order correlation coefficient, ++>、/>And->Respectively B i And B j Is a pearson product moment correlation coefficient, a spearman order correlation coefficient and a kendel order correlation coefficient,/>Is B i And B j Final correlation coefficient of (a);
a time weighted adjacency matrix is established, and the following formula is used:
；
wherein H is Z Is a time weighted adjacency matrix;
and constructing space-time diagram structure data, and obtaining a space-time weighted adjacent matrix based on the space weighted adjacent matrix and the time weighted adjacent matrix to obtain the space-time diagram structure data, wherein the formula is as follows:
Z（t）=G z H z ；
Q={q 1 ，q 2 ，…，q N1 }；
A（t）=（Q，γ，Z（t））；
where Q is a node set, Q is a node, a (t) is space-time diagram structure data at time t, γ is a connection set between nodes, and Z (t) is a space-time weighted adjacency matrix at time t.
3. The artificial intelligence based medical laboratory air quality monitoring system of claim 1, wherein: the air quality monitoring model constructing module constructs an air quality monitoring model based on space-time structural diagram data A (t) of a historical air quality monitoring data set, and specifically comprises the following contents:
encoding, performing encoding to obtain low-dimensional graph embedding, wherein the content is as follows:
the node embedding is calculated based on the GraphSAGE algorithm, and the formula is as follows:
；
；
in the method, in the process of the invention,is the embedding of node i at time t, q j Is node j, N i (t) is a node set adjacent to node i at time t, N j (t) is the set of nodes adjacent to node j at time t, z ij (t) is the connection weight of node i and node j at time t, +.>Is the embedding of node j at the first layer of time t, d l Is the embedded size of layer l;
updating node embedding of the next layer, wherein the formula is as follows:
；
；
wherein Z is l Is the connection weight matrix of layer l, concat is the aggregation operator, reLU is a nonlinear function,is the embedded estimate of the first +1 layer of node i at time t, +.>Is the embedding of node i at the first +1 layer of time t,is->The L2 norm of (2);
embedding time context information, wherein air quality monitoring data are periodic within u weeks v days, and embedding information h corresponding to the corresponding day in u weeks week Information h corresponding to the corresponding hour embedded in v days hour ；
Computational graph embedding, the formula used is as follows:
；
；
in the formula, h A (t) is the time t at which the ReLU function will be usedGraph embedding to low dimension>Is the final graph embedding combined at time t, Z A Is a weight matrix of the space-time structural diagram data A (t), is +.>The node i is embedded from the 1 st layer to the L th layer at the time t, and L is the embedded layer number;
decoding, the content is as follows:
the recovery node is embedded using the following formula:
；
in the method, in the process of the invention,is the restored node embedded->Is a weight matrix to be trained;
the single node embedding is resumed using the following formula:
；
in the formula, h i (t) is the embedding of node i at time t, and un stack is the cancel stack function;
the connection weights are restored using the following formula:
；
；
；
；
wherein d o Is the dimension of the connection weight, d L Is the number of layers in which the node is embedded,and->Is a weight matrix, h j (t) is the embedding of node j at time t,/->Is the estimated value of the connection weight of node i and node j at time t, z ij (t) is the connection weight of node i and node j at time t, σ is the Sigmoid function;
the reconstruction error is calculated using the MSE loss function, using the following formula:
；
where K (t) is the reconstruction error at time t, gamma is the connection set at time t, e ij Is an index of the connection relationship.
4. The artificial intelligence based medical laboratory air quality monitoring system of claim 1, wherein: the data preprocessing module deletes incorrect, irrelevant and repeated air quality monitoring data existing in the historical air quality monitoring data set, and performs missing value processing and data normalization processing.
5. The artificial intelligence based medical laboratory air quality monitoring system of claim 1, wherein: the data acquisition module deploys a plurality of air quality monitoring stations in the medical laboratory, acquires air quality monitoring data in the medical laboratory through the air quality monitoring stations, constructs a historical air quality monitoring dataset by collecting historical air quality monitoring data in the medical laboratory, and constructs a real-time air quality monitoring dataset by acquiring real-time air quality monitoring data in the medical laboratory.
6. The artificial intelligence based medical laboratory air quality monitoring system of claim 1, wherein: the air quality abnormality monitoring module presets an abnormality threshold delta, a real-time air quality monitoring data set is input into the air quality monitoring model, when the reconstruction error K (t) is not less than delta, the air quality in the medical laboratory is in an abnormal state, and the system sends an alarm signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311335738.9A CN117074627B (en) | 2023-10-16 | 2023-10-16 | Medical laboratory air quality monitoring system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311335738.9A CN117074627B (en) | 2023-10-16 | 2023-10-16 | Medical laboratory air quality monitoring system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117074627A true CN117074627A (en) | 2023-11-17 |
| CN117074627B CN117074627B (en) | 2024-01-09 |
Family
ID=88704653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311335738.9A Active CN117074627B (en) | 2023-10-16 | 2023-10-16 | Medical laboratory air quality monitoring system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117074627B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350175A (en) * | 2023-12-04 | 2024-01-05 | 河北东医生物科技有限公司 | Artificial intelligent ecological factor air environment quality monitoring method and system |
Citations (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423414A (en) * | 2017-07-28 | 2017-12-01 | 西安交通大学 | A kind of process industry complex electromechanical systems fault source tracing method based on information transmission model |
| WO2018214060A1 (en) * | 2017-05-24 | 2018-11-29 | 北京质享科技有限公司 | Small-scale air quality index prediction method and system for city |
| CN111738054A (en) * | 2020-04-17 | 2020-10-02 | 北京理工大学 | Behavior anomaly detection method based on space-time self-encoder network and space-time CNN |
| CN111831870A (en) * | 2020-06-12 | 2020-10-27 | 北京百度网讯科技有限公司 | Method and device for detecting abnormality of spatio-temporal data, electronic device and storage medium |
| CN111949749A (en) * | 2020-07-30 | 2020-11-17 | 中国科学技术大学 | High-order graph convolution network-based air quality monitoring station position recommendation method |
| CN112036075A (en) * | 2020-08-11 | 2020-12-04 | 中国环境监测总站 | Abnormal data judgment method based on environmental monitoring data association relation |
| CN113326981A (en) * | 2021-05-26 | 2021-08-31 | 北京交通大学 | Atmospheric environment pollutant prediction model based on dynamic space-time attention mechanism |
| CN113516304A (en) * | 2021-06-29 | 2021-10-19 | 上海师范大学 | Space-time joint prediction method and device for regional pollutants based on space-time graph network |
| US20210342722A1 (en) * | 2020-12-23 | 2021-11-04 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Air quality prediction model training method, air quality prediction method, electronic device and storage medium |
| CN113744541A (en) * | 2021-05-17 | 2021-12-03 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Road network discharge loss space-time distribution reconstruction method and system for confrontation graph convolution network |
| US20210389290A1 (en) * | 2020-06-12 | 2021-12-16 | Chinese Research Academy Of Environmental Sciences | Intelligent Monitoring and Analysis Method for Air Pollution and Device Thereof |
| CN113919231A (en) * | 2021-10-25 | 2022-01-11 | 北京航天创智科技有限公司 | PM2.5 concentration space-time change prediction method and system based on space-time diagram neural network |
| CN114240000A (en) * | 2021-12-31 | 2022-03-25 | 北京工业大学 | Air quality prediction method based on space-time graph convolution network |
| CN114648095A (en) * | 2022-02-28 | 2022-06-21 | 南京邮电大学 | Air quality concentration inversion method based on deep learning |
| CN114676121A (en) * | 2022-03-30 | 2022-06-28 | 重庆大学 | Missing monitoring data filling method based on multi-scale space-time memory shared network |
| CN114694767A (en) * | 2022-05-31 | 2022-07-01 | 山东科技大学 | PM2.5 concentration prediction method based on space-time diagram ordinary differential equation network |
| CN114841400A (en) * | 2022-03-25 | 2022-08-02 | 哈尔滨工程大学 | Air quality prediction method based on multi-task space-time diagram convolution |
| WO2022160902A1 (en) * | 2021-01-28 | 2022-08-04 | 广西大学 | Anomaly detection method for large-scale multivariate time series data in cloud environment |
| CN114968997A (en) * | 2022-05-11 | 2022-08-30 | 浙江大学 | Sintering end point forecasting method based on space-time feature extraction |
| KR102440752B1 (en) * | 2022-04-08 | 2022-09-07 | 주식회사 알고리고 | Device and method for monitoring driver's biometric information abnormality through multi-sampling sensor fusion |
| CN115200850A (en) * | 2022-07-19 | 2022-10-18 | 西安交通大学 | Mechanical equipment anomaly detection method under explicit representation of multi-point sample structure information |
| WO2022217839A1 (en) * | 2021-04-14 | 2022-10-20 | 江南大学 | Air quality prediction method based on deep spatiotemporal similarity |
| CN115293280A (en) * | 2022-08-17 | 2022-11-04 | 西安交通大学 | Power equipment system anomaly detection method based on space-time feature segmentation reconstruction |
| CN115310367A (en) * | 2022-09-01 | 2022-11-08 | 康志文 | Mine air quality monitoring system based on LSTM neural network |
| CN115345279A (en) * | 2022-08-10 | 2022-11-15 | 中国电信股份有限公司 | Multi-index abnormality detection method and device, electronic equipment and storage medium |
| CN115629160A (en) * | 2022-10-21 | 2023-01-20 | 重庆邮电大学 | Air pollutant concentration prediction method and system based on space-time diagram |
| CN115796359A (en) * | 2022-11-28 | 2023-03-14 | 浙江大学 | PM2.5 space-time prediction method based on depth Koopman operator |
| CN115795996A (en) * | 2022-09-30 | 2023-03-14 | 合肥泰瑞数创科技有限公司 | Real network diagram-based city data real-time management method and system of graph neural network |
| CN116090333A (en) * | 2022-12-14 | 2023-05-09 | 东南大学 | Urban public space disaster modeling and preventing system based on perception blind area estimation |
| CN116187555A (en) * | 2023-02-16 | 2023-05-30 | 华中科技大学 | Traffic flow prediction model construction method and prediction method based on self-adaptive dynamic diagram |
| CN116229036A (en) * | 2023-05-06 | 2023-06-06 | 山东国研自动化有限公司 | Data acquisition system, method, computer device and storage medium |
| CN116665130A (en) * | 2023-06-07 | 2023-08-29 | 河海大学 | Space-time diagram-based dam safety monitoring multivariate time sequence anomaly detection method |
| CN116760742A (en) * | 2023-06-21 | 2023-09-15 | 南京南瑞信息通信科技有限公司 | Network traffic anomaly detection method and system based on multi-stage hybrid space-time fusion |
| CN116881671A (en) * | 2023-09-04 | 2023-10-13 | 山东智明环保工程有限公司 | Atmospheric pollution tracing method and system based on neural network |
-
2023
- 2023-10-16 CN CN202311335738.9A patent/CN117074627B/en active Active
Patent Citations (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018214060A1 (en) * | 2017-05-24 | 2018-11-29 | 北京质享科技有限公司 | Small-scale air quality index prediction method and system for city |
| CN107423414A (en) * | 2017-07-28 | 2017-12-01 | 西安交通大学 | A kind of process industry complex electromechanical systems fault source tracing method based on information transmission model |
| CN111738054A (en) * | 2020-04-17 | 2020-10-02 | 北京理工大学 | Behavior anomaly detection method based on space-time self-encoder network and space-time CNN |
| CN111831870A (en) * | 2020-06-12 | 2020-10-27 | 北京百度网讯科技有限公司 | Method and device for detecting abnormality of spatio-temporal data, electronic device and storage medium |
| US20210389290A1 (en) * | 2020-06-12 | 2021-12-16 | Chinese Research Academy Of Environmental Sciences | Intelligent Monitoring and Analysis Method for Air Pollution and Device Thereof |
| CN111949749A (en) * | 2020-07-30 | 2020-11-17 | 中国科学技术大学 | High-order graph convolution network-based air quality monitoring station position recommendation method |
| CN112036075A (en) * | 2020-08-11 | 2020-12-04 | 中国环境监测总站 | Abnormal data judgment method based on environmental monitoring data association relation |
| US20210342722A1 (en) * | 2020-12-23 | 2021-11-04 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Air quality prediction model training method, air quality prediction method, electronic device and storage medium |
| WO2022160902A1 (en) * | 2021-01-28 | 2022-08-04 | 广西大学 | Anomaly detection method for large-scale multivariate time series data in cloud environment |
| WO2022217839A1 (en) * | 2021-04-14 | 2022-10-20 | 江南大学 | Air quality prediction method based on deep spatiotemporal similarity |
| CN113744541A (en) * | 2021-05-17 | 2021-12-03 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Road network discharge loss space-time distribution reconstruction method and system for confrontation graph convolution network |
| CN113326981A (en) * | 2021-05-26 | 2021-08-31 | 北京交通大学 | Atmospheric environment pollutant prediction model based on dynamic space-time attention mechanism |
| CN113516304A (en) * | 2021-06-29 | 2021-10-19 | 上海师范大学 | Space-time joint prediction method and device for regional pollutants based on space-time graph network |
| CN113919231A (en) * | 2021-10-25 | 2022-01-11 | 北京航天创智科技有限公司 | PM2.5 concentration space-time change prediction method and system based on space-time diagram neural network |
| CN114240000A (en) * | 2021-12-31 | 2022-03-25 | 北京工业大学 | Air quality prediction method based on space-time graph convolution network |
| CN114648095A (en) * | 2022-02-28 | 2022-06-21 | 南京邮电大学 | Air quality concentration inversion method based on deep learning |
| CN114841400A (en) * | 2022-03-25 | 2022-08-02 | 哈尔滨工程大学 | Air quality prediction method based on multi-task space-time diagram convolution |
| CN114676121A (en) * | 2022-03-30 | 2022-06-28 | 重庆大学 | Missing monitoring data filling method based on multi-scale space-time memory shared network |
| KR102440752B1 (en) * | 2022-04-08 | 2022-09-07 | 주식회사 알고리고 | Device and method for monitoring driver's biometric information abnormality through multi-sampling sensor fusion |
| CN114968997A (en) * | 2022-05-11 | 2022-08-30 | 浙江大学 | Sintering end point forecasting method based on space-time feature extraction |
| CN114694767A (en) * | 2022-05-31 | 2022-07-01 | 山东科技大学 | PM2.5 concentration prediction method based on space-time diagram ordinary differential equation network |
| CN115200850A (en) * | 2022-07-19 | 2022-10-18 | 西安交通大学 | Mechanical equipment anomaly detection method under explicit representation of multi-point sample structure information |
| CN115345279A (en) * | 2022-08-10 | 2022-11-15 | 中国电信股份有限公司 | Multi-index abnormality detection method and device, electronic equipment and storage medium |
| CN115293280A (en) * | 2022-08-17 | 2022-11-04 | 西安交通大学 | Power equipment system anomaly detection method based on space-time feature segmentation reconstruction |
| CN115310367A (en) * | 2022-09-01 | 2022-11-08 | 康志文 | Mine air quality monitoring system based on LSTM neural network |
| CN115795996A (en) * | 2022-09-30 | 2023-03-14 | 合肥泰瑞数创科技有限公司 | Real network diagram-based city data real-time management method and system of graph neural network |
| CN115629160A (en) * | 2022-10-21 | 2023-01-20 | 重庆邮电大学 | Air pollutant concentration prediction method and system based on space-time diagram |
| CN115796359A (en) * | 2022-11-28 | 2023-03-14 | 浙江大学 | PM2.5 space-time prediction method based on depth Koopman operator |
| CN116090333A (en) * | 2022-12-14 | 2023-05-09 | 东南大学 | Urban public space disaster modeling and preventing system based on perception blind area estimation |
| CN116187555A (en) * | 2023-02-16 | 2023-05-30 | 华中科技大学 | Traffic flow prediction model construction method and prediction method based on self-adaptive dynamic diagram |
| CN116229036A (en) * | 2023-05-06 | 2023-06-06 | 山东国研自动化有限公司 | Data acquisition system, method, computer device and storage medium |
| CN116665130A (en) * | 2023-06-07 | 2023-08-29 | 河海大学 | Space-time diagram-based dam safety monitoring multivariate time sequence anomaly detection method |
| CN116760742A (en) * | 2023-06-21 | 2023-09-15 | 南京南瑞信息通信科技有限公司 | Network traffic anomaly detection method and system based on multi-stage hybrid space-time fusion |
| CN116881671A (en) * | 2023-09-04 | 2023-10-13 | 山东智明环保工程有限公司 | Atmospheric pollution tracing method and system based on neural network |
Non-Patent Citations (7)
| Title |
|---|
| 凌启东;袁冠;王敏;王鸿磊;: "基于信息融合的开放式空气质量监测系统的研究", 电子测量与仪器学报, no. 05 * |
| 周志光;胡迪欣;刘亚楠;陈伟锋;陶煜波;林海;苏为华;: "面向空气质量监测数据时空多维属性的可视分析方法", 计算机辅助设计与图形学学报, no. 08 * |
| 李艳萍;赵晓宇;: "基于LSTM的空气质量预测方法", 科技与创新, no. 07 * |
| 聂斌;胡雪;王曦;: "基于最近邻分析的空气质量时空数据异常点识别", 统计研究, no. 08 * |
| 董婷;赵俭辉;胡勇;: "基于时空优化深度神经网络的AQI等级预测", 计算机工程与应用, no. 21 * |
| 邓雨荣;张炜;梁俊斌;邬蓉蓉;: "基于时间序列分析的油中产气数据趋势测度", 智能电网, no. 08 * |
| 郝舒欣;吕然;刘婕;刘悦;徐东群;: "空气污染对人群就诊影响时间序列分析的数据前处理方法", 环境与健康杂志, no. 05 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350175A (en) * | 2023-12-04 | 2024-01-05 | 河北东医生物科技有限公司 | Artificial intelligent ecological factor air environment quality monitoring method and system |
| CN117350175B (en) * | 2023-12-04 | 2024-03-12 | 河北东医生物科技有限公司 | Artificial intelligent ecological factor air environment quality monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117074627B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117074627B (en) | Medical laboratory air quality monitoring system based on artificial intelligence | |
| CN102361014B (en) | State monitoring and fault diagnosis method for large-scale semiconductor manufacture process | |
| CN112987675B (en) | Method, device, computer equipment and medium for anomaly detection | |
| CN113723010B (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
| CN102340811B (en) | Method for carrying out fault diagnosis on wireless sensor networks | |
| CN115169479A (en) | Remote monitoring method, system and storage medium for sewage treatment process | |
| CN111737909A (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN114626890A (en) | Abnormal user detection method based on graph structure learning | |
| CN112367303B (en) | Distributed self-learning abnormal flow collaborative detection method and system | |
| CN114265913A (en) | Space-time prediction algorithm based on federal learning on industrial Internet of things edge equipment | |
| CN116520799A (en) | Complex industrial process fault detection method based on space-time variation diagram attention self-encoder | |
| CN117272196A (en) | Industrial time sequence data anomaly detection method based on time-space diagram attention network | |
| CN114663742A (en) | Road surface abnormity detection method and system based on unsupervised learning | |
| CN111881413A (en) | Multi-source time sequence missing data recovery method based on matrix decomposition | |
| CN117688464B (en) | Hidden danger analysis method and system based on multi-source sensor data | |
| CN116663613A (en) | Multi-element time sequence anomaly detection method for intelligent Internet of things system | |
| CN117708738A (en) | Sensor time sequence anomaly detection method and system based on multi-modal variable correlation | |
| CN117392556A (en) | Carbon sink monitoring method based on improved LSTM algorithm | |
| CN117725548A (en) | Abnormality detection method and device, electronic equipment and storage medium | |
| CN112163020A (en) | Multi-dimensional time series anomaly detection method and system | |
| CN113469228A (en) | Power load abnormal value identification method based on data flow space-time characteristics | |
| CN115330362A (en) | Engineering progress data processing method and system | |
| CN114689351A (en) | Equipment fault predictive diagnosis system and method | |
| Gao et al. | Outlier detection in temporal and spatial sequences via correlation analysis based on graph neural networks | |
| CN114863356B (en) | Group activity identification method and system based on residual aggregation graph network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Artificial Intelligence based Air Quality Monitoring System for Medical Laboratories Granted publication date: 20240109 Pledgee: Shizhong Branch of Qilu Bank Co.,Ltd. Pledgor: Sanke Intelligent (Shandong) Group Co.,Ltd. Registration number: Y2024980035930 |